Update README.md

README.md

@@ -30,8 +30,32 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
+import gymnasium
+from stable_baselines3 import PPO
+from stable_baselines3.common.env_util import make_vec_env
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.monitor import Monitor
 from huggingface_sb3 import load_from_hub
 
+repo_id = "AdanLee/ppo-LunarLander-v2"  # The repo_id
+filename = "ppo-LunarLander-v2.zip"  # The model filename.zip
+
+# When the model was trained on Python 3.8 the pickle protocol is 5
+# But Python 3.6, 3.7 use protocol 4
+# In order to get compatibility we need to:
+# 1. Install pickle5 (we done it at the beginning of the colab)
+# 2. Create a custom empty object we pass as parameter to PPO.load()
+custom_objects = {
+    "learning_rate": 0.0,
+    "lr_schedule": lambda _: 0.0,
+    "clip_range": lambda _: 0.0,
+}
+
+checkpoint = load_from_hub(repo_id, filename)
+model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)
+
+eval_env = Monitor(gym.make("LunarLander-v2"))
+mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
 ...
 ```